AI Paper Atlas

Research map / Continual learning / Online and replay-based

DualNet: Continual Learning, Fast and Slow

Quang Pham, Chenghao Liu, Steven HOI

NeurIPS 2021 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 59 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use DualNet's separate slow self-supervised learner and fast adaptation learnerContinual learning with reduced ResNet18 · Split miniImageNet-TAACC: 68.04±1.23 -> 73.20±0.68Improved
Use DualNet's separate slow self-supervised learner and fast adaptation learnerContinual learning with reduced ResNet18 · Split miniImageNet-TFACC: 25.26±1.81 -> 37.56±0.52Improved
Use DualNet's separate slow self-supervised learner and fast adaptation learnerContinual learning with ResNet18 · CORE50-TAACC: 54.17±0.85 -> 57.64±1.36Improved
Use DualNet's separate slow self-supervised learner and fast adaptation learnerContinual learning with ResNet18 · CORE50-TFACC: 28.10±0.80 -> 38.76±1.52Improved
Use the slow learner on unlabeled stream samplesDualNet · Split miniImageNet-TA, ρ = 10%ACC: 49.80±2.66 -> 54.03±2.88Improved
Use the slow learner on unlabeled stream samplesDualNet · Split miniImageNet-TA, ρ = 25%ACC: 55.90±0.86 -> 62.80±2.40Improved
Replace Look-ahead with SGD for the Barlow Twins slow learner (ablation)DualNet · Split miniImageNet-TAACC: 73.20±0.68 -> 64.20/-2.37Hurt
Use SimCLR instead of Barlow Twins with Look-ahead (ablation)DualNet · Split miniImageNet-TAACC: 73.20±0.68 -> 72.13±0.44Hurt
Replace Barlow Twins with classification loss using Look-ahead (ablation)DualNet · Split miniImageNet-TAACC: 73.20±0.68 -> 70.96±1.08Hurt
Use Look-ahead instead of SGD for the slow learner (ablation)DualNet with Barlow Twins · Split miniImageNet-TAACC: 64.20/-2.37 -> 73.20±0.68Improved
Increase SSL updates between labeled batches from n=1 to n=20 (ablation)DualNet, memory 50 · Split miniImageNet-TAACC: 72.26±0.71 -> 74.53±1.18Improved
Increase SSL updates between labeled batches from n=1 to n=20 (ablation)DualNet, memory 100 · Split miniImageNet-TAACC: 74.67±1.05 -> 77.86±0.43Improved

Later papers that compared with this method

2 later accepted papers report DualNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy